+ All Categories
Home > Documents > Morphing

Morphing

Date post: 26-Feb-2016
Category:
Upload: lolita
View: 45 times
Download: 0 times
Share this document with a friend
Description:
Morphing. CSE 590 Computational Photography Tamara Berg. Announcements. HW3 online after class Submit facial point locations by Sunday night (March 17) Final due date for HW extended to April 1. Image Morphing - Women in Art video. http://youtube.com/watch?v=nUDIoN-_Hxs. Morphing . - PowerPoint PPT Presentation
Popular Tags:
38
Morphing CSE 590 Computational Photography Tamara Berg
Transcript
Page 1: Morphing

Morphing

CSE 590 Computational PhotographyTamara Berg

Page 2: Morphing

Announcements

HW3 online after class

Submit facial point locations by Sunday night (March 17)

Final due date for HW extended to April 1

Page 3: Morphing

Image Morphing - Women in Art video

http://youtube.com/watch?v=nUDIoN-_Hxs

Page 4: Morphing

Morphing

http://www.youtube.com/watch?v=L0GKp-uvjO0

Page 5: Morphing

Morphing = Object Averaging

The aim is to find “an average” between two objects• Not an average of two images of objects…• …but an image of the average object!• How can we make a smooth transition in time?

– Do a “weighted average” over time t

How do we know what the average object looks like?• We haven’t a clue!• But we can often fake something reasonable

– Usually required user/artist input

Page 6: Morphing

Idea #1: Cross-Dissolve

Interpolate whole images:Imagehalfway = (1-t)*Image1 + t*image2

This is called cross-dissolve in film industry

But what if the images aren’t aligned?

Page 7: Morphing

Idea #2: Align, then cross-disolve

Align first, then cross-dissolve• Alignment using global warp – picture still valid

Page 8: Morphing

Dog Averaging

What to do?• Cross-dissolve doesn’t work• Global alignment doesn’t work

– Cannot be done with a global transformation (e.g. affine)• Any ideas?

Feature matching!• Nose to nose, tail to tail, etc.• This is a local (non-parametric) warp

Page 9: Morphing

Idea #3: Local warp, then cross-dissolve

Morphing procedure: for every t,1. Find the average shape (the “mean dog”)

• local warping2. Find the average color

• Cross-dissolve the warped images

Page 10: Morphing

Local (non-parametric) Image Warping

Need to specify a more detailed warp function• Global warps were functions of a few (2,4,8) parameters• Non-parametric warps u(x,y) and v(x,y) can be defined

independently for every single location x,y!• Once we know vector field u,v we can easily warp each pixel

Page 11: Morphing

Image Warping – non-parametricMove control points to specify a spline warpSpline produces a smooth vector field

Page 12: Morphing

Warp specification - denseHow can we specify the warp?

Specify corresponding spline control points• interpolate to a complete warping function

But we want to specify only a few points, not a grid

Page 13: Morphing

Warp specification - sparseHow can we specify the warp?

Specify corresponding points• interpolate to a complete warping function• How do we do it?

How do we go from feature points to pixels?

Page 14: Morphing

Triangular Mesh

1. Input correspondences at key feature points2. Define a triangular mesh over the points

• Same mesh in both images!• Now we have triangle-to-triangle correspondences

Page 15: Morphing

TriangulationsA triangulation of set of points in the plane is a partition of the convex hull to triangles whose vertices are the points, and do not contain other points.

There are an exponential number of triangulations of a point set.

Page 16: Morphing

An O(n3) Triangulation AlgorithmRepeat until impossible:

• Select two sites.• If the edge connecting them does not intersect previous

edges, keep it.

Page 17: Morphing

“Quality” Triangulations

Let (Ti) = (i1, i2 ,.., i3) be the vector of angles in the triangulation T in increasing order:• A triangulation T1 is “better” than T2 if the smallest angle of T1 is larger than the smallest angle of T2

• Delaunay triangulation is the “best” (maximizes the smallest angles)

good bad

Page 18: Morphing

Improving a TriangulationIn any convex quadrangle, an edge flip is possible. If this flip improves the triangulation locally, it also improves the global triangulation.

If an edge flip improves the triangulation, the first edge is called “illegal”.

Page 19: Morphing

Illegal Edges

Lemma: An edge pq is illegal iff one of its opposite vertices is inside the circle defined by the other three vertices.

Proof: By Thales’ theorem.

Theorem: A Delaunay triangulation does not contain illegal edges.Corollary: A triangle is Delaunay iff the circle through its vertices is

empty of other sites.Corollary: The Delaunay triangulation is not unique if more than

three sites are co-circular.

p

q

Page 20: Morphing

Naïve Delaunay Algorithm

Start with an arbitrary triangulation. Flip any illegal edge until no more exist.Could take a long time to terminate.

Page 21: Morphing

Delaunay Triangulation by Duality

Draw the dual to the Voronoi diagram by connecting each two neighboring sites in the Voronoi diagram.• The DT may be constructed in O(nlogn) time• This is what Matlab’s delaunay function uses

Page 22: Morphing

Triangular Mesh

1. Input correspondences at key feature points2. Define a triangular mesh over the points

• Same mesh in both images!• Now we have triangle-to-triangle correspondences

3. Warp each triangle separately from source to destination• How do we warp a triangle?• 3 points = affine warp!

Page 23: Morphing

Example: warping triangles

Given two triangles: ABC and A’B’C’ in 2D (12 numbers) Need to find transform T to transfer all pixels from one to

the other.How can we compute the transformation matrix:

T(x,y)

?

A

B

C A’C’

B’

Source Destination

11001''

yx

fedcba

yx

Page 24: Morphing

Image MorphingWe know how to warp one image into the other, but how

do we create a morphing sequence?1. Create an intermediate shape (by interpolation)2. Warp both images towards it3. Cross-dissolve the colors in the newly warped images

Page 25: Morphing

Warp interpolationHow do we create an intermediate warp at time t?

• Assume t = [0,1]• Simple linear interpolation of each feature pair• (1-t)*p1+t*p0 for corresponding features p0 and p1

Page 26: Morphing

Morphing & matting

Extract foreground first to avoid artifacts in the background

Slide by Durand and Freeman

Page 27: Morphing

Summary of morphing1. Define corresponding points2. Define triangulation on points

• Use same triangulation for both images

3. For each t = 0:step:1a. Compute the average shape (weighted average of points)b. For each triangle in the average shape

– Get the affine projection to the corresponding triangles in each image

– For each pixel in the triangle, find the corresponding points in each image and set value to weighted average

c. Save the image as the next frame of the sequence

Page 28: Morphing

View Morphing

Steven M. Seitz, Charles R. Dyer

Page 29: Morphing

View Morphing: Key Idea

Beier-Neely morph is NOT shape-preserving!• distortions• un-natural

A Shape-Distorting MorphSource: Steven M. Seitz, Charles R. Dyer

Slide credit: Irwin Chiu Hau

Page 30: Morphing

View Morphing: Key Idea

View morphing uses 3D shape preserving morph!• no distortions• natural

A morph is 3D shape preserving if the results of twodifferent views represent new views of the same object

A Shape-Distorting MorphSource: Steven M. Seitz, Charles R. Dyer

View morphing fixesthese intermediate

steps!

Slide credit: Irwin Chiu Hau

Page 31: Morphing

Why do we care?

View morphing is efficientProduces new views without

• 3D modeling• Taking additional photos

View morphing creates impressive effects• Camera motion• Image morphing

trueSpaceSource: www.caligari.com

Slide credit: Irwin Chiu Hau

Page 32: Morphing

Consider parallel views

Page 33: Morphing

How to do View Morphing?

View morphing in three steps1. Prewarp two images2. Compute a morph between the

prewarped images3. Postwarp each in between images

produced by the morph

Slide credit: Irwin Chiu Hau

Page 34: Morphing

Results

Page 35: Morphing

Results

Facial view morphsSource: Steven M. Seitz, Charles R. Dyer

Slide credit: Irwin Chiu Hau

Page 36: Morphing

Results

Page 37: Morphing

Results

Top: Image MorphBottom: View Morph

Page 38: Morphing

Have a good spring break!


Recommended